Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds real behavioral context beyond the annotations: cursor advancement via the since parameter, and the trial-expiry handoff to create_watch. However, readOnlyHint=false is unusual for a poll and the description never explains what that mutation is (cursor/state advance) or what happens if you poll an expired trial — presumably an error, but unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core instruction and the since/cursor mechanic are front-loaded, which is good. But 'Free. ... Free — no payment required.' is stated twice, wasting a whole clause in an already short description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should characterize the response; it only notes that a new cursor accompanies it, saying nothing about the alert payload shape. The trial-expiry path is covered, but what a caller gets back from a successful poll is not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters are already documented. The description's 'Pass since={last seq you saw}' largely restates the schema's 'highest alert seq already seen; 0 on first poll' and adds no format or edge-case detail beyond it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (poll) and a specific resource (a trial watch created by try_watch), tying it directly to the sibling that creates it. An agent can distinguish this from poll_alerts (paid watches) and check_now without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the lifecycle clearly: use this while the trial is active, and once it expires move to create_watch for a paid watch (which bundles 7 days of polling and renewal). It never names poll_alerts explicitly, so the trial-vs-paid polling choice is only implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.